Skip to content
IFAI

Model rankings

740 models · 4 boards · 2 sources

Artificial AnalysisIntelligence IndexArenaText arena

Intelligence Index · A composite of several evaluations · Updated November 6, 2025

Smartest
GPT-5 Codex (high)OpenAI68.5Intelligence
Best open model
MiniMax-M2MiniMax61.4Intelligence
Best value
Gemma 3n E4B InstructGoogle620 pts/$Value
Best from China
MiniMax-M2MiniMax61.4Intelligence
Top three by Intelligence
1GPT-5 Codex (high)OpenAI68.5
2GPT-5 (high)OpenAI68.5
3o3OpenAI65.5
Top three open models
1MiniMax-M2MiniMax · #8 overall61.4
2gpt-oss-120B (high)OpenAI · #9 overall60.5
3DeepSeek V3.1 Terminus (Reasoning)DeepSeek · #14 overall57.7
This week's changes
MiniMax-M2Intelligence · #8New
Chirp 3: HDSpeech · #20New
Maya1Speech · #21New
Qwen3 VL 235B A22B (Reasoning)Intelligence · #23New
Sonic 3Speech · #23New
RankChangeModelIntelligencePrice $/MSpeed tok/sFirst token
1—GPT-5 Codex (high)ClosedOpenAI68.5$3.4——
2—GPT-5 (high)ClosedOpenAI68.5$3.4——
3—GPT-5 (medium)ClosedOpenAI66.4$3.4——
4—o3ClosedOpenAI65.5$3.5——
5—Grok 4ClosedxAI65.3$6.0——
6—o3-proClosedOpenAI65.3$35——
7—GPT-5 mini (high)ClosedOpenAI64.3$0.69——
8—Claude 4.5 Sonnet (Reasoning)ClosedAnthropic62.7$6.0——
9—GPT-5 (low)ClosedOpenAI61.8$3.4——
10—GPT-5 mini (medium)ClosedOpenAI60.8$0.69——
11▲ 4gpt-oss-120B (high)OpenOpenAI60.5$0.26——
12▼ 1Grok 4 Fast (Reasoning)ClosedxAI60.3$0.28——
13▼ 1Gemini 2.5 ProClosedGoogle59.6$3.4——
14▼ 1o4-mini (high)ClosedOpenAI59.6$1.9——
15▼ 1Claude 4.1 Opus (Reasoning)ClosedAnthropic59.3$30——
16—Grok 3 mini Reasoning (high)ClosedxAI57.1$0.35——
17—Claude 4 Sonnet (Reasoning)ClosedAnthropic56.5$6.0——
18—Claude 4.5 Haiku (Reasoning)ClosedAnthropic54.6$2.0——
19—Gemini 2.5 Flash Preview (Sep '25) (Reasoning)ClosedGoogle54.4$0.85——
20—Claude 4 Opus (Reasoning)ClosedAnthropic54.2$30——
21—Gemini 2.5 Pro Preview (Mar' 25)ClosedGoogle54.1$3.4——
22—Gemini 2.5 Pro Preview (May' 25)ClosedGoogle53.2$3.4——
23▲ 22gpt-oss-20B (high)OpenOpenAI52.4$0.095——
24▼ 1Apriel-v1.5-15B-ThinkerOpenServiceNow51.6$0.000——
25▼ 1Gemini 2.5 Flash (Reasoning)ClosedGoogle51.2$0.85——
26▼ 1GPT-5 nano (high)ClosedOpenAI51.0$0.14——
27▼ 1o3-mini (high)ClosedOpenAI50.8$1.9——
28▼ 1Claude 3.7 Sonnet (Reasoning)ClosedAnthropic49.9$6.0——
29▼ 1Claude 4.5 Sonnet (Non-reasoning)ClosedAnthropic49.6$6.0——
30▼ 1GPT-5 nano (medium)ClosedOpenAI49.3$0.14——
31▼ 1Grok Code Fast 1ClosedxAI48.7$0.53——
32▼ 1o3-miniClosedOpenAI48.1$1.9——
33▼ 1o1-proClosedOpenAI48.0$263——
34▼ 1Gemini 2.5 Flash-Lite Preview (Sep '25) (Reasoning)ClosedGoogle47.9$0.18——
35Newgpt-oss-120B (low)OpenOpenAI47.5$0.26——
36▼ 2o1ClosedOpenAI47.2$26——
37▼ 2Gemini 2.5 Flash Preview (Sep '25) (Non-reasoning)ClosedGoogle46.7$0.85——
38▼ 2Sonar Reasoning ProClosedPerplexity46.3$0.000——
39▼ 2Gemini 2.5 Flash Preview (Reasoning)ClosedGoogle45.8$0.000——
40▼ 2Grok 3ClosedxAI45.3$6.0——
41▼ 2Llama Nemotron Super 49B v1.5 (Reasoning)OpenNVIDIA45.2$0.18——
42▼ 2o1-previewClosedOpenAI44.9$29——
43▼ 2Claude 4.1 Opus (Non-reasoning)ClosedAnthropic44.6$30——
44▼ 2Claude 4 Sonnet (Non-reasoning)ClosedAnthropic44.4$6.0——
45Newgpt-oss-20B (low)OpenOpenAI44.3$0.095——
46▼ 3GPT-5 (minimal)ClosedOpenAI43.5$3.4——
47▼ 3GPT-4.1ClosedOpenAI43.4$3.5——
48▼ 2GPT-4.1 miniClosedOpenAI42.5$0.70——
49▼ 2Claude 4 Opus (Non-reasoning)ClosedAnthropic42.3$30——
50▼ 2GPT-5 (ChatGPT)ClosedOpenAI41.8$3.4——

Intelligence over time

Each maker's best model at the time on the Artificial Analysis Intelligence Index, by the month it was released.

Gained most · Anthropic +57.2Highest now · Anthropic 64.6Gap between highest and lowest 18.1 ptsTime range Nov 2025 – Nov 2026
64.6Anthropic60.0Google56.9OpenAI50.1Meta46.5Kimi

Arena data comes from the leaderboard dataset it publishes on Hugging Face (CC BY 4.0). Only each board's overall leaderboard is used; scores and ranks are unchanged. dataset · CC BY 4.0

Artificial Analysis data comes from its API (artificialanalysis.ai). Scores are unchanged; ranks follow the scores. artificialanalysis.ai

Open or closed follows the license Arena gives; prices and Artificial Analysis intelligence show only where model names match, otherwise “—”.